© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 51545
    Prev
    Next
    INDEX
    Explanations

    Locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     co
    -0.07
     quasi
    -0.07
    -ban
    -0.07
    quiler
    -0.07
     quas
    -0.07
     quos
    -0.07
    Co
    -0.07
     उ
    -0.07
     quienes
    -0.07
    Qui
    -0.07
    POSITIVE LOGITS
    akka
    0.09
     καν
    0.08
    ത്തി
    0.08
    лаў
    0.08
    ിധ
    0.08
     kant
    0.08
    lef
    0.08
    ochemistry
    0.08
     weisen
    0.08
    ീകര
    0.08
    Activations Density 0.001%

    No Known Activations